Efficient online algorithms for fast-rate regret bounds under sparsity

Authors: Pierre Gaillard, Olivier Wintenberger

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We consider the problem of online convex optimization in two different settings: arbitrary and i.i.d. sequence of convex loss functions. In both settings, we provide efficient algorithms whose cumulative excess risks are controlled with fast-rate sparse bounds.
Researcher Affiliation Academia Pierre Gaillard INRIA, ENS, PSL Research University Paris, France pierre.gaillard@inria.fr Olivier Wintenberger Sorbonne Université, CNRS, LPSM Paris, France olivier.wintenberger@upmc.fr
Pseudocode Yes Algorithm 1 Squint BOA with multiple constant learning rates assigned to each parameter... Algorithm 2 SABOA Sparse Acceleration of BOA
Open Source Code No The paper is theoretical and does not mention releasing any source code or provide any links to code repositories.
Open Datasets No The paper is purely theoretical and does not use or reference any publicly available datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe any dataset splits for validation or other purposes.
Hardware Specification No The paper is theoretical and does not mention any hardware specifications used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not provide specific details about an experimental setup, such as hyperparameters or training configurations.